Venue
Year

* denotes equal contribution

2026

CHI 2026

"What Keeps Fans on the Silent Field?": Understanding Lean-Back Football Fans via AI Sports Broadcasting in Non-Event Time

Kyusik Kim, Jaehoon Choi, Hoyeol Yang, Hyunsoo Choi, Minchae Kim, Minjeong Shin, Bongwon Suh

ACM CHI, Barcelona, Spain

We developed ARUA, a prototype that positions users as 'directors' of their own AI commentary, tailoring its social presence, emotional tone, and cognitive load.

Paper
ACL 2026

Feeling Right vs. Being Right: How AI Sycophancy Affects Value-Laden Deliberation

Jeongwoo Ryu, Soomin Kim, Jinsu Eun, Kyusik Kim, Changhoon Oh, Bongwon Suh

Annual Meeting of the ACL

Studying how sycophantic AI behavior impacts the quality of value-laden deliberation and moral reasoning.

Findings of ACL 2026

Visual Interference in Speech Evaluation: Cultural Asymmetry and Cross-Modal Bias in MLLMs

Kyusik Kim*, Hyunwoo Yoo*, Jaehoon Choi, Gail Rosen, Bongwon Suh

Findings of the ACL

Investigating how visual information creates cross-modal interference in speech evaluation by multimodal LLMs, revealing cultural asymmetries.

Findings of ACL 2026

Whose Voice, Whose Avatar? Gender Matching Bias in Multimodal AI Teammates

Kyusik Kim*, Jaehoon Choi*, Hyunwoo Yoo, Bongwon Suh

Findings of the ACL

Uncovering gender matching biases in multimodal AI teammate configurations.

Findings of ACL 2026

CliniCAST: Benchmarking Acoustic Grounding and Text Dominance in Medical Triage

Kyusik Kim*, Hyunwoo Yoo*, Jaehoon Choi, Kitae Kim, Gail Rosen, Bongwon Suh

Findings of the ACL

A benchmark for evaluating how well multimodal models ground acoustic cues versus text in medical triage.

SIGIR 2026

Who Is Shopping With You? How Persona Design Shapes Cognitive and Social Engagement in AI Shopping Agents

Hyungwoo Song*, Kyusik Kim*, Hyeonseok Jeon, Minjeong Shin, Bongwon Suh

ACM SIGIR, Melbourne

Examining how persona designs for AI shopping agents influence users' cognitive and social engagement.

SIGIR 2026

Mine over Yours: How Authorship Biases Evaluation in Generative Information Retrieval

Jeongwoo Ryu, Kyusik Kim, Soomin Kim, Jinsu Eun, Changhoon Oh, Bongwon Suh

ACM SIGIR

Revealing authorship biases in how users evaluate generated content in IR systems.

CogSci 2026

Co-Overcooked: Cognitive Constraints on Partner Modeling in Human-AI Team Composition

Junghwan Kim*, Dongseok Heo*, Kyusik Kim, Jung Lee, Bongwon Suh

Annual Meeting of the Cognitive Science Society

Using a collaborative cooking game (Co-Overcooked), we show that partner modeling capacity constrains viable human-AI team configurations in nonlinear ways, revealing expectation conflicts when multiple humans hold divergent models of a shared AI partner.

2025

CHI 2025

BleacherBot: AI Agent as a Sports Co-Viewing Partner

Kyusik Kim*, Hyungwoo Song*, Jeongwoo Ryu, Changhoon Oh, Bongwon Suh

ACM CHI, Yokohama

Designed a fine-tuned LLM-based AI agent for sports co-viewing that significantly enhances users' emotional engagement.

Paper
CHI 2025

Cinema Multiverse Lounge: Enhancing Film Appreciation via Multi-Agent Conversations

Jeongwoo Ryu*, Kyusik Kim*, Dongseok Heo, Hyungwoo Song, Changhoon Oh, Bongwon Suh

ACM CHI, Yokohama

A novel multi-agent system for film appreciation where users converse with AI personas of directors, actors, and audiences.

Paper
Findings of ACL 2025

Blinded by Context: Unveiling the Halo Effect of MLLM in AI Hiring

Kyusik Kim*, Jeongwoo Ryu*, Hyeonseok Jeon, Bongwon Suh

Findings of the ACL

Revealing how contextual cues create halo effects in multimodal LLM-based hiring systems.

Paper
Findings of ACL 2025

DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues

Kyochul Jang, Donghyeon Lee, Kyusik Kim, Dongseok Heo, Taewhoo Lee, Woojeong Kim, Bongwon Suh

Findings of the ACL

A benchmark for evaluating LLM tool-use capabilities in complex multi-party dialogue scenarios.

Paper
SIGIR 2025

Conversational Argument Search Under Selective Exposure: Strategies for Balanced Perspective Access

Kyusik Kim*, Jeongwoo Ryu*, Dongseok Heo, Hyungwoo Song, Changhoon Oh, Bongwon Suh

ACM SIGIR

Developing strategies to counteract selective exposure in conversational argument search.

Paper

2024

CHI EA 2024

Exploring the Impact of User-Participated Customization in Experiencing Chatbot Failure

Hyungwoo Song, Kyusik Kim, Kitae Kim, Jeongwoo Ryu, Bongwon Suh

CHI Extended Abstracts

Investigating how user participation in chatbot customization affects tolerance of chatbot failures.

Paper
SIGIR 2024

Self-Referential Review: Exploring the Impact of Self-Reference Effect in Review

Kyusik Kim*, Hyungwoo Song*, Bongwon Suh

ACM SIGIR

Investigating how self-reference effects influence review behavior and evaluation quality.

Paper
Findings of EMNLP 2024

Will LLMs Sink or Swim? Exploring Decision-Making Under Pressure

Kyusik Kim, Hyeonseok Jeon, Jeongwoo Ryu, Bongwon Suh

Findings of EMNLP

Exploring how LLMs make decisions under pressure, revealing systematic biases in high-stakes scenarios.

Paper
DASFAA 2024

SymphoNEI: Symphony of Node and Edge Inductive Representations on Large Heterophilic Graphs

Kyusik Kim, Bongwon Suh

DASFAA (LNCS)

Combining node and edge representations for inductive learning on large heterophilic graphs.

Paper
DASFAA 2024

HopLearn: Leveraging Multi-Hop Neighbors and Learnable Parameters for GNNs with Missing Node Features

Kyusik Kim, Bongwon Suh

DASFAA (LNCS)

Addressing missing node features in GNNs by leveraging multi-hop neighborhood information.

Paper